53 lines
1.3 KiB
Python
53 lines
1.3 KiB
Python
import re
|
|
import subprocess
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
DATUM_IZPISKA = re.compile(r"Datum izpiska\s+(\d{2})\.(\d{2})\.(\d{4})")
|
|
# raneme nlb-izpisek based on datum izpiska
|
|
|
|
def pdf_to_text(pdf_path):
|
|
result = subprocess.run(
|
|
["pdftotext", "-layout", str(pdf_path), "-"],
|
|
capture_output=True, text=True, check=True,
|
|
)
|
|
return result.stdout
|
|
|
|
|
|
def find_date(text):
|
|
match = DATUM_IZPISKA.search(text)
|
|
if not match:
|
|
return None
|
|
day, month, year = match.groups()
|
|
return f"{year}-{month}-{day}"
|
|
|
|
|
|
def unique_target(dir_path, stem, suffix, current_path):
|
|
target = dir_path / f"{stem}{suffix}"
|
|
n = 2
|
|
while target.exists() and target != current_path:
|
|
target = dir_path / f"{stem}_{n}{suffix}"
|
|
n += 1
|
|
return target
|
|
|
|
|
|
def main():
|
|
pdf_dir = Path(sys.argv[1])
|
|
|
|
for pdf_path in sorted(pdf_dir.glob("*.pdf")):
|
|
text = pdf_to_text(pdf_path)
|
|
date = find_date(text)
|
|
if not date:
|
|
print(f"skip {pdf_path.name}: no 'Datum izpiska' found")
|
|
continue
|
|
|
|
target = unique_target(pdf_dir, f"izpisek_{date}", pdf_path.suffix, pdf_path)
|
|
if target == pdf_path:
|
|
continue
|
|
pdf_path.rename(target)
|
|
print(f"{pdf_path.name} -> {target.name}")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|